The Agent Skills Directory

[SAFE]: The skill does not contain any executable scripts, shell commands, or subprocess calls. Its operations are limited to processing text and providing instructional guidelines.
[SAFE]: No network activity, external downloads, or data exfiltration vectors were detected. All file references (e.g., brand-profile.md, audience.md) are to local assets within the skill's context.
[SAFE]: The skill does not employ any obfuscation, hidden encoding, or homoglyph attacks. All text and metadata are clear and consistent with the skill's stated purpose.
[SAFE]: The skill includes explicit defensive logic, such as instructing the agent to set honest expectations and to avoid making analytics claims that the underlying platform cannot support.
[SAFE]: No persistence mechanisms, privilege escalation attempts, or dynamic context injection patterns were found.

hashtag-strategy